Modeling of overall volumetric oxygen transfer by plunging jets of different geometries

The paper explores the potential of computational techniques in the modeling of overall volumetric oxygen transfer by plunging jets of different geometries, namely circular, square, rectangular and rectangular with rounded edge. The results predicted from neural network, support vector machines and Gaussian process techniques are compared in terms of correlation coefficient, root mean square error and coefficient of determination. The outcome suggests the utility of all these computational techniques in the designing and performance evaluation of plunging jets oxygenation systems of different geometric shapes. However, support vector machines have performed better in comparison to other techniques. It has predicted overall volumetric oxygen transfer coefficient with a correlation coefficient of 0.985, coefficient of determination of 0.968 and root mean square error of 0.002. Further, the scattering (within 15 percent) is lowest in case of support vector machines approach. A comparison of results suggests that support vector machines works well and can be successfully used in modeling oxygen transfer by plunging jets of different geometries and configurations.